Retention Score: Quantifying Jailbreak Risks for Vision Language Models
- Zaitang Li
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025
Conference paper
Publications
230 results for Adversarial Robustness and Privacy
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
- Xiaomeng Xu
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025
Conference paperPEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks
- Huzaifa Arif
- Keerthiram Murugesan
- et al.
- 2025
- IEEE SaTML 2025
Conference paperVP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis
- Chia-Yi Hsu
- Jia-You Chen
- et al.
- 2025
- ICASSP 2025
Conference paperIs My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation
- Maya Anderson
- Guy Amit
- et al.
- 2025
- ICISSP 2025
Short paperThe inherent adversarial robustness of analog in-memory computing
- Corey Lammie
- Julian Büchel
- et al.
- 2025
- Nature Communications
PaperExploring Research and Tools in AI Security: A Systematic Mapping Study
- Sidhant Narula
- Mohammad Ghasemigol
- et al.
- 2025
- IEEE Access
PaperPrivacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
- Kristjan Greenewald
- Yuancheng Yu
- et al.
- 2024
- NeurIPS 2024
Conference paperUnified Lookup Tables: Privacy-Preserving Foundation Models
- Nikita Janakarajan
- Irina Espejo Morales
- et al.
- 2024
- NeurIPS 2024
Workshop paperAttack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
- Ambrish Rawat
- Stefan Schoepf
- et al.
- 2024
- NeurIPS 2024
Workshop